Intrinsic Image Diffusion for Single-view Material Estimation
CVPR 2024(2024)
摘要
We present Intrinsic Image Diffusion, a generative model for appearance
decomposition of indoor scenes. Given a single input view, we sample multiple
possible material explanations represented as albedo, roughness, and metallic
maps. Appearance decomposition poses a considerable challenge in computer
vision due to the inherent ambiguity between lighting and material properties
and the lack of real datasets. To address this issue, we advocate for a
probabilistic formulation, where instead of attempting to directly predict the
true material properties, we employ a conditional generative model to sample
from the solution space. Furthermore, we show that utilizing the strong learned
prior of recent diffusion models trained on large-scale real-world images can
be adapted to material estimation and highly improves the generalization to
real images. Our method produces significantly sharper, more consistent, and
more detailed materials, outperforming state-of-the-art methods by 1.5dB on
PSNR and by 45% better FID score on albedo prediction. We demonstrate the
effectiveness of our approach through experiments on both synthetic and
real-world datasets.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要